VANETs improve the safety and efficiency of the road traffic through powerful cooperative applications that gather and broadcast real-time road traffic information. Routing in VANETs is a critical issue in today's research due to the high speed of the nodes, rate of topology variability, and real-time restrictions of their applications. Hence, the research community is very active with hot topics, creating new VANET protocols and improving the existent ones (Lee et al. 2009). The Ad hoc On Demand Vector (AODV) routing proto-col (Perkins et al. 2003), which is optimized in this study, has been previously analyzed for use in vehicular environments. Some authors have proposed changes to its parameter configuration to gain huge improvements over its quality-of-service (QoS) in VANETs (Said and Nakamura 2014). The configuration parameters of AODV have a strongly non-linear relationship with each other and a complex influence on its final performance. In fact, they represent a mix of discrete plus continuous variables which makes it a hard challenge to find the "best" configuration in a real-world scenario. Thus, exact and enumerative methods are not applicable for solving the underlying optimization problem of finding the "best" AODV configuration, because they require critically long execution times to perform the search, and because we are far from having a traditional analytical equation. In this context, soft computing methods are a promising approach to find accurate QoS-efficient AODV configurations in rea-sonable times.

With the growing interest in underwater exploration and monitoring, Autonomous Underwater Vehicles (AUVs) have become essential. The recent interest in onboard Deep Learning (DL) has advanced real-time environmental interaction capabilities relying on efficient and accurate vision-based DL models. However, the predominant use of sonar in underwater environments, characterized by limited training data and inherent noise, poses challenges to model robustness. This autonomy improvement raises safety concerns for deploying such models during underwater operations, potentially leading to hazardous situations. This paper aims to provide the first comprehensive overview of sonar-based DL under the scope of robustness. It studies sonar-based DL perception task models, such as classification, object detection, segmentation, and SLAM. Furthermore, the paper systematizes sonar-based state-of-the-art datasets, simulators, and robustness methods such as neural network verification, out-of-distribution, and adversarial attacks. This paper highlights the lack of robustness in sonar-based DL research and suggests future research pathways, notably establishing a baseline sonar-based dataset and bridging the simulation-to-reality gap.

Large Language Models (LLMs) are gaining popularity in the field of robotics. However, LLM-based robots are limited to simple, repetitive motions due to the poor integration between language models, robots, and the environment. This paper proposes a novel approach to enhance the performance of LLM-based autonomous manipulation through Human-Robot Collaboration (HRC). The approach involves using a prompted GPT-4 language model to decompose high-level language commands into sequences of motions that can be executed by the robot. The system also employs a YOLO-based perception algorithm, providing visual cues to the LLM, which aids in planning feasible motions within the specific environment. Additionally, an HRC method is proposed by combining teleoperation and Dynamic Movement Primitives (DMP), allowing the LLM-based robot to learn from human guidance. Real-world experiments have been conducted using the Toyota Human Support Robot for manipulation tasks. The outcomes indicate that tasks requiring complex trajectory planning and reasoning over environments can be efficiently accomplished through the incorporation of human demonstrations.

Aerial manipulator, which is composed of an UAV (Unmanned Aerial Vehicle) and a multi-link manipulator and can perform aerial manipulation, has shown great potential of applications. However, dynamic coupling between the UAV and the manipulator makes it difficult to control the aerial manipulator with high performance. In this paper, system modeling and control problem of the aerial manipulator are studied. Firstly, an UAV dynamic model is proposed with consideration of the dynamic coupling from an attached manipulator, which is treated as disturbance for the UAV. In the dynamic model, the disturbance is affected by the variable inertia parameters of the aerial manipulator system. Then, based on the proposed dynamic model, a disturbance compensation robust $H_{\infty}$ controller is designed to stabilize flight of the UAV while the manipulator is in operation. Finally, experiments are conducted and the experimental results demonstrate the feasibility and validity of the proposed control scheme.

Abstract--Offline optimal planning of trajectories for redundant we go through the whole process of planning and executing robots along prescribed task space paths is usually a time-optimal trajectory on a real robot, and discuss some broken down into two consecutive processes: first, the task practical details, such as trajectory smoothness and actuator space path is inverted to obtain a joint space path, then, the saturation, aiding the practitioners in deploying our algorithm latter is parametrized with a time law. If the two processes effectively. Currently, the algorithm's applicability is limited are separated, they cannot optimize the same objective function, to those cases where hours are available for planning, hence ultimately providing sub-optimal results. In this paper, it is not well-suited for those cases where the robot activity a unified approach is presented where dynamic programming has to change frequently. By replacing the underlying dynamic is the underlying optimization technique. Its flexibility allows programming engine with a different methodology, such as accommodating arbitrary constraints and objective functions, randomized algorithms, the planning time could be controlled thus providing a generic framework for optimal planning of real to be upper-bounded, thus returning the most efficient solution systems. To demonstrate its applicability to a real world scenario, that can be achieved in the time available for reconfiguring the the framework is instantiated for time-optimality on Franka production. Other applications of interest include optimal ground Emika's Panda robot.

Autonomous driving (AD) perception today relies heavily on deep learning based architectures requiring large scale annotated datasets with their associated costs for curation and annotation. The 3D semantic data are useful for core perception tasks such as obstacle detection and ego-vehicle localization. We propose a new dataset, Navya 3D Segmentation (Navya3DSeg), with a diverse label space corresponding to a large scale production grade operational domain, including rural, urban, industrial sites and universities from 13 countries. It contains 23 labeled sequences and 25 supplementary sequences without labels, designed to explore self-supervised and semi-supervised semantic segmentation benchmarks on point clouds. We also propose a novel method for sequential dataset split generation based on iterative multi-label stratification, and demonstrated to achieve a +1.2% mIoU improvement over the original split proposed by SemanticKITTI dataset. A complete benchmark for semantic segmentation task was performed, with state of the art methods. Finally, we demonstrate an Active Learning (AL) based dataset distillation framework. We introduce a novel heuristic-free sampling method called ego-pose distance based sampling in the context of AL. A detailed presentation on the dataset is available here https://www.youtube.com/watch?v=5m6ALIs-s20.

Balancing parallel robots throughout their workspace while avoiding the use of balancing masses and respecting design practicality constraints is difficult. Medical robots demand such compact and lightweight designs. This paper considers the difficult task of achieving optimal approximate balancing of a parallel robot throughout a desired task-based dexterous workspace using balancing springs only. While it is possible to achieve perfect balancing in a path, only approximate balancing may be achieved without the addition of balancing masses. Design considerations for optimal robot base placement and the effects of placement of torsional balancing springs are presented. Using a modal representation for the balancing torque requirements, we use recent results on the design of wire-wrapped cam mechanisms to achieve balancing throughout a task-based workspace. A simulation study shows that robot base placement can have a detrimental effect on the attainability of a practical design solution for static balancing. We also show that optimal balancing using torsional springs is best achieved when all springs are at the actuated joints and that the wire-wrapped cam design can significantly improve the performance of static balancing. The methodology presented in this paper provides practical design solutions that yield simple, lightweight and compact designs suitable for medical applications where such traits are paramount.

Impressive advances in acquisition and sharing technologies have made the growth of multimedia collections and their applications almost unlimited. However, the opposite is true for the availability of labeled data, which is needed for supervised training, since such data is often expensive and time-consuming to obtain. While there is a pressing need for the development of effective retrieval and classification methods, the difficulties faced by supervised approaches highlight the relevance of methods capable of operating with few or no labeled data. In this work, we propose a novel manifold learning algorithm named Rank Flow Embedding (RFE) for unsupervised and semi-supervised scenarios. The proposed method is based on ideas recently exploited by manifold learning approaches, which include hypergraphs, Cartesian products, and connected components. The algorithm computes context-sensitive embeddings, which are refined following a rank-based processing flow, while complementary contextual information is incorporated. The generated embeddings can be exploited for more effective unsupervised retrieval or semi-supervised classification based on Graph Convolutional Networks. Experimental results were conducted on 10 different collections. Various features were considered, including the ones obtained with recent Convolutional Neural Networks (CNN) and Vision Transformer (ViT) models. High effective results demonstrate the effectiveness of the proposed method on different tasks: unsupervised image retrieval, semi-supervised classification, and person Re-ID. The results demonstrate that RFE is competitive or superior to the state-of-the-art in diverse evaluated scenarios.

Due to a huge volume of information in many domains, the need for classification methods is imperious. In spite of many advances, most of the approaches require a large amount of labeled data, which is often not available, due to costs and difficulties of manual labeling processes. In this scenario, unsupervised and semi-supervised approaches have been gaining increasing attention. The GCNs (Graph Convolutional Neural Networks) represent a promising solution since they encode the neighborhood information and have achieved state-of-the-art results on scenarios with limited labeled data. However, since GCNs require graph-structured data, their use for semi-supervised image classification is still scarce in the literature. In this work, we propose a novel approach, the Manifold-GCN, based on GCNs for semi-supervised image classification. The main hypothesis of this paper is that the use of manifold learning to model the graph structure can further improve the GCN classification. To the best of our knowledge, this is the first framework that allows the combination of GCNs with different types of manifold learning approaches for image classification. All manifold learning algorithms employed are completely unsupervised, which is especially useful for scenarios where the availability of labeled data is a concern. A broad experimental evaluation was conducted considering 5 GCN models, 3 manifold learning approaches, 3 image datasets, and 5 deep features. The results reveal that our approach presents better accuracy than traditional and recent state-of-the-art methods with very efficient run times for both training and testing.

Humans coordinate the abundant degrees of freedom (DoFs) of hands to dexterously perform tasks in everyday life. We imitate human strategies to advance the dexterity of multi-DoF robotic hands. Specifically, we enable a robot hand to grasp multiple objects by exploiting its kinematic redundancy, referring to all its controllable DoFs. We propose a human-like grasp synthesis algorithm to generate grasps using pairwise contacts on arbitrary opposing hand surface regions, no longer limited to fingertips or hand inner surface. To model the available space of the hand for grasp, we construct a reachability map, consisting of reachable spaces of all finger phalanges and the palm. It guides the formulation of a constrained optimization problem, solving for feasible and stable grasps. We formulate an iterative process to empower robotic hands to grasp multiple objects in sequence. Moreover, we propose a kinematic efficiency metric and an associated strategy to facilitate exploiting kinematic redundancy. We validated our approaches by generating grasps of single and multiple objects using various hand surface regions. Such grasps can be successfully replicated on a real robotic hand.